Multiversal Simulacra: Understanding Hypotheticals and Possible Worlds Through Simulation

2021/10/02 by Michael D. Ekstrand, Ekstrand, Michael D.
Computer Science · #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Information Retrieval (cs.IR) #Social and Information Networks (cs.SI) #cs.HC #cs.IR #cs.SI

paper · pdf · doi:10.48550/arxiv.2110.00811

Contribution to the SimuRec Workshop at RecSys 2021

arxiv created 2021/10/02 · arxiv updated 2021/10/05

Abstract

Recommender systems research is concerned with many aspects of recommender system behavior and effects than simply its effectiveness, and simulation can be a powerful tool for uncovering these effects. In this brief position paper, I identify specific types of research that simulation is uniquely well-suited to address along with a hierarchy of simulation types.

Related

• Simulation as Experiment: An Empirical Critique of Simulation Research on Recommender Systems
• Recommendation System Simulations: A Discussion of Two Key Challenges
• T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems
• Simulations in Recommender Systems: An industry perspective
• Synthetic Data-Based Simulators for Recommender Systems: A Survey